opencv-mtcnn
opencv-mtcnn copied to clipboard
Why does rgbImg need a .t()?
Hello, I have one question about the input data processing in MTCNNDetector::detect().
rgbImg.convertTo(rgbImg, CV_32FC3); rgbImg = rgbImg.t();
Why does rgbImg need a .t()?
I have the same question.
I think rgbImg = rgbImg.t();
converts (or rather simulates) the dimension to NCHW, which is required by the CNN module. blobFromImage actually gives the output in NCHW format.